KevinLee26/kanana-1.5-8b-instruct-2505-Safe-DPO

TEXT GENERATIONPricing:Input $0.37 / Cached $0.074 / Output $0.38Concurrent Unit Cost:1Model Size:8BQuant:FP8Context Size:8kTool Calling:SupportedPublished:Aug 14, 2026Architecture:Transformer Featherless Exclusive Cold

The KevinLee26/kanana-1.5-8b-instruct-2505-Safe-DPO is an 8 billion parameter instruction-tuned language model with an 8192 token context length. Developed by KevinLee26, this model is fine-tuned using Direct Preference Optimization (DPO) for enhanced safety and instruction following. It is designed for general-purpose conversational AI and instruction-based tasks, offering improved response quality through its DPO training.

Loading preview...

Model Overview

This model, KevinLee26/kanana-1.5-8b-instruct-2505-Safe-DPO, is an 8 billion parameter instruction-tuned language model. It features an 8192 token context length, making it suitable for processing moderately long inputs and generating coherent responses. The model has been fine-tuned using Direct Preference Optimization (DPO), a method known for aligning models with human preferences and improving safety characteristics.

Key Capabilities

  • Instruction Following: Designed to accurately interpret and execute user instructions.
  • Safety Enhancements: Benefits from DPO training, which typically leads to safer and more aligned outputs.
  • General-Purpose Conversational AI: Capable of engaging in a wide range of conversational tasks.

Use Cases

  • Chatbots and Virtual Assistants: Ideal for applications requiring robust instruction following and safe interactions.
  • Content Generation: Can be used for generating text based on specific prompts and guidelines.
  • Research and Development: Provides a solid base for further fine-tuning or experimentation in language model alignment.